AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

ScaleNet: Searching for the Model to Scale

Jiyang Xie, Xiu Su, Shan You, Zhanyu Ma, Fei Wang, Chen Qian

ECCV 2022 · Architectures and efficiency › Neural architecture search · approach: One-shot and few-shot supernets

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add hierarchical sampling strategy (HSS) instead of uniform sampling (ablation)ScaleNet · ImageNet-100top-1 accuracy (%): s0 84.16 -> 84.76; s4 90.02 -> 90.46Improved
add HSS instead of uniform sampling (ablation)super-supernet training · path rankingPearson coefficient (%): 35.3 -> 73.6Improved
add HSS instead of uniform sampling (ablation)super-supernet training · path rankingSpearman and Kendall (%): 80.1 -> 83.9; 64.1 -> 66.2Improved
raise maximum scaling stage M from 1 to 3 (ablation)ScaleNet MCEA · ImageNet-100top-1 accuracy (%): s0 84.06 -> 84.76; s4 90.30 -> 90.46Mixed
raise MCEA iterations T from 1 to 4 (ablation)ScaleNet MCEA · ImageNet-100top-1 accuracy (%): s0 84.18 -> 84.76; s1 86.34 -> 87.18Improved
raise MCEA iterations T from 4 to 8 (ablation)ScaleNet MCEA · ImageNet-100top-1 accuracy (%): s0 84.76 -> 84.50; s4 90.46 -> 90.36No clear effect
use proposed exponential generalization function instead of linear or squared (ablation)ScaleNet s4 · ImageNet-100top-1 accuracy (%): 90.46Improved
search base model and scaling strategies jointly (ScaleNet) versus prior NAS scaling pipelinesScaleNet · search costGPU/TPU days: 1,228 -> 485Improved
transfer ScaleNet-S0 instead of EfficientNet-B0fine-tuning · CIFAR-100top-1 accuracy (%): 88.1 -> 88.4Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy